Dense metal corrosion depth estimation
Introduction: Metal corrosion detection is important for protecting lives and property. X-ray inspection systems are widely used because of their good penetrability and visual presentation capability. They can visually display both external and internal corrosion defects. However, existing X-ray-bas...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-09-01
|
| Series: | Frontiers in Physics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphy.2023.1277710/full |
| _version_ | 1797677617582702592 |
|---|---|
| author | Yanping Li Honggang Li Yong Guan Xinyu Zhang Xiaomei Zhao |
| author_facet | Yanping Li Honggang Li Yong Guan Xinyu Zhang Xiaomei Zhao |
| author_sort | Yanping Li |
| collection | DOAJ |
| description | Introduction: Metal corrosion detection is important for protecting lives and property. X-ray inspection systems are widely used because of their good penetrability and visual presentation capability. They can visually display both external and internal corrosion defects. However, existing X-ray-based defect detection methods cannot present and estimate the dense corrosion depths. To solve this problem, we propose a dense metal corrosion depth estimation method based on image segmentation and inpainting.Methods: The proposed method employs an image segmentation module to segment metal corrosion defects and an image inpainting module to remove these segmented defects. It then calculates the pixel-level dense corrosion depths using the X-ray images before and after inpainting. Moreover, to address the difficulty of acquiring training images with ground-truth dense corrosion depth annotations, we propose a virtual data generation method for creating virtual corroded metal X-ray images and their corresponding ground-truth annotations.Results: Experiments on both virtual and real datasets show that the proposed method successfully achieves accurate dense metal corrosion depth estimation.Discussion: In conclusion, the proposed virtual data generation method can provide effective and sufficient training samples, and the proposed dense metal corrosion depth estimation framework can produce accurate dense corrosion depths. |
| first_indexed | 2024-03-11T22:47:53Z |
| format | Article |
| id | doaj.art-6bc47921a3544e60b472b32c095a314f |
| institution | Directory Open Access Journal |
| issn | 2296-424X |
| language | English |
| last_indexed | 2024-03-11T22:47:53Z |
| publishDate | 2023-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physics |
| spelling | doaj.art-6bc47921a3544e60b472b32c095a314f2023-09-22T07:44:47ZengFrontiers Media S.A.Frontiers in Physics2296-424X2023-09-011110.3389/fphy.2023.12777101277710Dense metal corrosion depth estimationYanping Li0Honggang Li1Yong Guan2Xinyu Zhang3Xiaomei Zhao4School of Information and Electrical Engineering, Shandong Jianzhu University, Jinan, ChinaSchool of Information and Electrical Engineering, Shandong Jianzhu University, Jinan, ChinaSHI Changxu Advanced Material Innovation Center, Chinese Academy of Sciences, Shenyang, ChinaSHI Changxu Advanced Material Innovation Center, Chinese Academy of Sciences, Shenyang, ChinaSchool of Information and Electrical Engineering, Shandong Jianzhu University, Jinan, ChinaIntroduction: Metal corrosion detection is important for protecting lives and property. X-ray inspection systems are widely used because of their good penetrability and visual presentation capability. They can visually display both external and internal corrosion defects. However, existing X-ray-based defect detection methods cannot present and estimate the dense corrosion depths. To solve this problem, we propose a dense metal corrosion depth estimation method based on image segmentation and inpainting.Methods: The proposed method employs an image segmentation module to segment metal corrosion defects and an image inpainting module to remove these segmented defects. It then calculates the pixel-level dense corrosion depths using the X-ray images before and after inpainting. Moreover, to address the difficulty of acquiring training images with ground-truth dense corrosion depth annotations, we propose a virtual data generation method for creating virtual corroded metal X-ray images and their corresponding ground-truth annotations.Results: Experiments on both virtual and real datasets show that the proposed method successfully achieves accurate dense metal corrosion depth estimation.Discussion: In conclusion, the proposed virtual data generation method can provide effective and sufficient training samples, and the proposed dense metal corrosion depth estimation framework can produce accurate dense corrosion depths.https://www.frontiersin.org/articles/10.3389/fphy.2023.1277710/fullcorrosion depth estimationimage segmentationimage inpaintingvirtual training data generationx-ray image |
| spellingShingle | Yanping Li Honggang Li Yong Guan Xinyu Zhang Xiaomei Zhao Dense metal corrosion depth estimation Frontiers in Physics corrosion depth estimation image segmentation image inpainting virtual training data generation x-ray image |
| title | Dense metal corrosion depth estimation |
| title_full | Dense metal corrosion depth estimation |
| title_fullStr | Dense metal corrosion depth estimation |
| title_full_unstemmed | Dense metal corrosion depth estimation |
| title_short | Dense metal corrosion depth estimation |
| title_sort | dense metal corrosion depth estimation |
| topic | corrosion depth estimation image segmentation image inpainting virtual training data generation x-ray image |
| url | https://www.frontiersin.org/articles/10.3389/fphy.2023.1277710/full |
| work_keys_str_mv | AT yanpingli densemetalcorrosiondepthestimation AT honggangli densemetalcorrosiondepthestimation AT yongguan densemetalcorrosiondepthestimation AT xinyuzhang densemetalcorrosiondepthestimation AT xiaomeizhao densemetalcorrosiondepthestimation |